NEURAL MODELER OF AUDIO SYSTEMS

A process for creating digital audio systems as well as a corresponding hardware system are disclosed. The process includes training a neural network that digitally models a reference audio system. The process further includes repeatedly performing a set of operations. The set of operations includes predicting by the neural network, a model output based upon an input, where the output approximates an expected output of the reference audio system, and the prediction is carried out in the time domain. The set of operations also includes applying a perceptual loss function to the neural network based upon a determined psychoacoustic property, wherein the perceptual loss function is applied in the frequency domain. Moreover, the set of operations includes adjusting the neural network responsive to the output of the perceptual loss function. The process further includes outputting a neural model file that can be loaded to generate a virtualization of the reference audio system.